Skip to content

Nautili.aivsOpenRouter

OpenRouter is a hosted endpoint for hundreds of models. Nautili runs on your own keys, in your own network if you want, and adds per-team spend, budgets and model allowlists.

Nautili.ai vs OpenRouter at a glance

OpenRouter is a marketplace you call. Nautili is a gateway that sits in front of the keys and seats you already pay for. Which one fits comes down to where your traffic runs and who needs to read the bill.

Choose Nautili if
  • Your traffic has to run on your own provider keys, inside your own network.
  • Finance wants spend by team and developer, including coding tool seats.
  • You spend more than $25K a month on your own keys and want the bigger fee-free allowance.
Choose OpenRouter if
  • You don't want to deploy anything, and one credit balance for every provider suits you.
  • You need Zero Data Retention per model group, or EU and US regional endpoints.
  • You rely on OpenRouter's speed and price shortcuts or its Auto Router.
Both give you
  • 500+ models behind one OpenAI-compatible API, at provider list price.
  • Provider ranking, fallbacks and automatic model selection.
  • Budgets, model and provider allowlists, and filters for PII and prompt injection.

Feature comparison

Routing, spend, governance and deployment, row by row, starting with where the two differ.

Where they differ · 7
Whose keysAccess
Nautili.aiManaged or your own

Managed keys, or your own provider keys, Claude seats and ChatGPT logins, passed through untouched on your own gateway.

OpenRouterCredits or your own

Prepaid OpenRouter credits, or your own provider keys, in which case the provider bills you directly.

Spend attributionSpend
Nautili.aiPerson, team, seat

Spend is split by person, team, department, service and seat, using a team tag on each request or the key owner. Each number is marked as reported by the provider or measured by the gateway.

OpenRouterKey and member

Spend is tracked per API key, organization member and workspace.

BudgetsGovernance
Nautili.aiManaged and your own keys

A hard dollar cap for a person, a key or a whole team, resetting daily, weekly, monthly or never. It applies to managed keys and to your own.

OpenRouterOwn keys left out by default

Guardrail budgets reset daily, weekly or monthly. Spend on your own keys only counts if you switch that setting on. Workspace budgets are Enterprise only.

Data handlingData
Nautili.aiStays in your network

On a self-hosted gateway, prompt text stays in your network by default. Prompts aren't retained unless you choose to keep them for 7, 30 or 90 days.

OpenRouterZDR and regions

Zero Data Retention per model group, set by guardrail or per request. EU and US regional domains need a Business or Enterprise plan.

EvalsQuality
Nautili.aiIncluded

Trials on live traffic, replays of past traffic, experiments on your own datasets, and a side-by-side compare of up to six models. A person always makes the final call on switching.

OpenRouterNot listed

There's no live-traffic trial or model promotion workflow in the OpenRouter docs.

DeploymentPlatform
Nautili.aiHosted or self-hosted

Hosted by Nautili, or run it yourself with Helm on Kubernetes or Docker Compose.

OpenRouterHosted only

A hosted service at openrouter.ai, with eu.openrouter.ai and us.openrouter.ai for in-region routing.

FeesPricing
Nautili.aiShare of spend

4% of inference spend, with tokens at provider list price. On your own keys, the first $50K a month carries no fee and the rest is 4%.

OpenRouterFee on credits

5.5% when you buy credits, with a $0.80 minimum, 5% in crypto and 8% on Business. Your own keys are free up to $25,000 of list-price usage a month, then 5%.

Where they match · 5
Model catalogAccess
Nautili.ai500+ models

More than 500 models from 70+ providers on Pay-as-you-go.

OpenRouter500+ models

More than 500 models from 80+ providers through one API.

Routing and fallbacksRouting
Nautili.aiIncluded

A routing profile for a team, person or key sets the default model, up to four fallbacks, how providers are ranked (cost, latency or throughput) and which ones are allowed or denied.

OpenRouterIncluded

Set provider order, sort by price, speed or latency, allow or skip providers, cap the price, and list fallback models.

Automatic model pickRouting
Nautili.aiOpt-in

Auto mode is off until you turn it on in a routing profile, and a 0 to 10 dial sets the balance between quality and cost.

OpenRouterIncluded

The Auto Router picks a model for each prompt, with a setting for how much to favour cost.

Access controlGovernance
Nautili.aiIncluded

Allow and ignore lists for models and providers, with * wildcards. One guardrail applies to each request. Shadow mode logs what it would have blocked before you enforce it. Requests on your own credentials still go through; on Nautili-issued keys a would-deny still fails.

OpenRouterIncluded

Model and provider allowlists on guardrails, assigned to a workspace, member or key. When several apply, the strictest rule wins.

Content rulesGovernance
Nautili.aiIncluded

Built-in detectors for emails, phone numbers, SSNs, card numbers, names, addresses and prompt injection, plus your own custom patterns. A rule can flag, redact or block.

OpenRouterIncluded

Prompt injection and jailbreak detection, PII redaction or blocking, and custom regex filters on guardrails.

Gateway fees at your monthly spend

Both charge the provider's list price for tokens, so the gateway fee is where the bills differ. Move the slider to see what each one adds in a month.

Who pays the provider

Based on both published price lists. OpenRouter measures its free allowance at its own list prices, and your provider still bills you for tokens on both.

Nautili fee$0$50K free, then 4%
OpenRouter fee$750$25K free, then 5%

Nautili saves you $750 a month at this level of usage.

Pricing compared

Both pass tokens through at the provider's list price. Nautili charges a percentage of what you spend on inference, and OpenRouter charges its fee when you buy credits.

Nautili.aiNautili pricing
4%platform fee on inference spend
  • Demo. Free starter credit to try Nautili, no card
  • Pay-as-you-go. 4% fee, tokens at provider list price
  • Your own keys. No fee on the first $50K a month, then 4%
  • Enterprise. Volume pricing, SSO/SAML and SCIM

Pay-as-you-go includes budgets, prompt caching and per-team attribution.

Try it free
5.5%fee on credit purchases
  • Free. Free models with daily request limits
  • Pay-as-you-go. 5.5% on credits, $0.80 minimum
  • Your own keys. No fee on the first $25,000 a month, then 5%
  • Business. 8% fee, with in-region routing

Enterprise plans list fee discounts and a custom allowance on your own keys.

When Nautili.ai is the better choice

Nautili is built for teams that keep their own provider contracts and have to account for the bill:

  1. Self-host the gateway with Helm or Docker Compose, and prompt text stays inside your network by default.
  2. Spend is broken out by People, Teams, Departments, Services and Seats, and each number tells you where it came from.
  3. Your own keys get $50K a month with no fee and 4% after that, compared with $25K and 5%.
  4. Trials score a cheaper candidate model on live traffic, and nothing changes until someone approves it.

When OpenRouter is the better choice

With OpenRouter there's no gateway to run at all. Pick it when:

  1. You want one key and one prepaid balance for 500+ models, with nothing to deploy.
  2. You need Zero Data Retention per model group, or EU and US regional domains on Business and Enterprise.
  3. You want price caps and speed or cost preferences set on each request.
  4. You want coding agents to sign in through your organization's OAuth, so there are no API keys to hand out.

How to switch from OpenRouter to Nautili.ai

Move one app or team at a time. OpenRouter can keep handling everything else until the last team has switched.

  1. 01Connect

    Change the base URL and the key

    Start on the Shared Gateway, which every team has from the Demo tier onward. It runs on managed keys and needs no install.

  2. 02Own keys

    Run your own gateway

    Install it with Docker Compose or Helm so your provider key, Claude seat or ChatGPT login passes straight through.

  3. 03Tag

    Tag requests by team and user

    Add a team and user tag to each request. For agents that run over many turns, add a session tag too.

  4. 04Govern

    Test budgets in shadow, then enforce

    Shadow mode logs what would have been blocked, so you can adjust limits before you enforce them. Requests on your own credentials still go through; on Nautili-issued keys a would-deny still fails.

Frequently asked questions

What teams usually ask before they switch.

Read the docs
  • What is the difference between Nautili.ai and OpenRouter?

    OpenRouter is a hosted endpoint for 500+ models that you pay for with prepaid credits or your own keys. Nautili is a gateway you can run in your own network, and it adds spend per team and per developer, budgets and model allowlists to the keys you already have.

  • Can I use my own provider keys with Nautili.ai?

    Yes. On a self-hosted gateway, requests on your own provider key, Claude seat or ChatGPT login pass through untouched while Nautili records usage and attribution. There's no platform fee on the first $50K a month on your own keys.

  • How do fees compare between Nautili.ai and OpenRouter?

    Nautili charges 4% of inference spend and nothing on the first $50K a month on your own keys. OpenRouter charges 5.5% when you buy credits, with a $0.80 minimum, and 5% on your own keys above $25,000 of list-price usage a month.

  • How do I move from OpenRouter to Nautili.ai?

    Change the base URL and the key in your OpenAI-compatible client. Both name models the same way, so most of yours carry over once you check them against the Nautili catalog. Add team and user tags to see spend by team.

  • When is OpenRouter the better choice?

    OpenRouter suits teams that don't want to deploy anything and like having one credit balance across providers. It's also a good fit when you need Zero Data Retention per model group or EU and US regional endpoints.

All comparisons

Point one URL at Nautili

Try the Demo tier on the Shared Gateway and see spend by team before you move anything off OpenRouter.